{"id":"W2904427283","doi":"10.1007/978-3-030-04375-9_30","title":"Adversarial Training for Dual-Stage Image Denoising Enhanced with Feature Matching","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Discriminator; Convolutional neural network; Pattern recognition (psychology); Noise reduction; Feature (linguistics); Benchmark (surveying); Noise (video); Image (mathematics); Video denoising; Computer vision","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002020826,0.0007691321,0.0008149465,0.0007617333,0.0006894762,0.001523143,0.002552545,0.0004268342,0.00002622861],"category_scores_gemma":[0.0001776376,0.0006483679,0.0002072777,0.0006068931,0.0008889964,0.001368158,0.0008118154,0.0009871962,0.00001870739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002893626,"about_ca_system_score_gemma":0.0009222169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001408138,"about_ca_topic_score_gemma":0.00005435101,"domain_scores_codex":[0.9951621,0.00007991849,0.0004943267,0.002067633,0.001092253,0.001103726],"domain_scores_gemma":[0.9964555,0.001028737,0.0004521265,0.001346983,0.0005021608,0.0002145054],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002961196,0.00004452271,0.000001614353,0.0002372301,0.0000817801,0.0005461585,0.02252131,0.0160383,0.03943925,0.01015044,0.0001443133,0.910499],"study_design_scores_gemma":[0.005753908,0.002355509,0.00003958093,0.004018168,0.0001212296,0.0006636695,0.00001250108,0.370206,0.13554,0.4691015,0.007424219,0.004763716],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002683403,0.0001414753,0.9933419,0.0004535543,0.002133615,0.000694113,0.00001261125,0.0002383102,0.002716119],"genre_scores_gemma":[0.01435951,0.000005925005,0.9808543,0.001239425,0.001604185,0.00001427275,0.000008740572,0.00007786301,0.001835769],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9057353,"threshold_uncertainty_score":0.9995968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02525006744884929,"score_gpt":0.2853881541568226,"score_spread":0.2601380867079733,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}